[IPSEC] proto: Move transport mode input path into xfrm_mode_transport

Now that we have xfrm_mode objects we can move the transport mode specific
input decapsulation code into xfrm_mode_transport.  This removes duplicate
code as well as unnecessary header movement in case of tunnel mode SAs
since we will discard the original IP header immediately.

This also fixes a minor bug for transport-mode ESP where the IP payload
length is set to the correct value minus the header length (with extension
headers for IPv6).

Of course the other neat thing is that we no longer have to allocate
temporary buffers to hold the IP headers for ESP and IPComp.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index e2e4771..c778223 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -119,6 +119,7 @@
 static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int ah_hlen;
+	int ihl;
 	struct iphdr *iph;
 	struct ip_auth_hdr *ah;
 	struct ah_data *ahp;
@@ -149,13 +150,14 @@
 	ah = (struct ip_auth_hdr*)skb->data;
 	iph = skb->nh.iph;
 
-	memcpy(work_buf, iph, iph->ihl*4);
+	ihl = skb->data - skb->nh.raw;
+	memcpy(work_buf, iph, ihl);
 
 	iph->ttl = 0;
 	iph->tos = 0;
 	iph->frag_off = 0;
 	iph->check = 0;
-	if (iph->ihl != 5) {
+	if (ihl > sizeof(*iph)) {
 		u32 dummy;
 		if (ip_clear_mutable_options(iph, &dummy))
 			goto out;
@@ -164,7 +166,7 @@
 		u8 auth_data[MAX_AH_AUTH_LEN];
 		
 		memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
-		skb_push(skb, skb->data - skb->nh.raw);
+		skb_push(skb, ihl);
 		ahp->icv(ahp, skb, ah->auth_data);
 		if (memcmp(ah->auth_data, auth_data, ahp->icv_trunc_len)) {
 			x->stats.integrity_failed++;
@@ -172,11 +174,8 @@
 		}
 	}
 	((struct iphdr*)work_buf)->protocol = ah->nexthdr;
-	skb->nh.raw = skb_pull(skb, ah_hlen);
-	memcpy(skb->nh.raw, work_buf, iph->ihl*4);
-	skb->nh.iph->tot_len = htons(skb->len);
-	skb_pull(skb, skb->nh.iph->ihl*4);
-	skb->h.raw = skb->data;
+	skb->h.raw = memcpy(skb->nh.raw += ah_hlen, work_buf, ihl);
+	__skb_pull(skb, ah_hlen + ihl);
 
 	return 0;
 
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 9d1881c..9bbdd449 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -143,10 +143,9 @@
 	int alen = esp->auth.icv_trunc_len;
 	int elen = skb->len - sizeof(struct ip_esp_hdr) - esp->conf.ivlen - alen;
 	int nfrags;
-	int encap_len = 0;
+	int ihl;
 	u8 nexthdr[2];
 	struct scatterlist *sg;
-	u8 workbuf[60];
 	int padlen;
 
 	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr)))
@@ -177,7 +176,6 @@
 	skb->ip_summed = CHECKSUM_NONE;
 
 	esph = (struct ip_esp_hdr*)skb->data;
-	iph = skb->nh.iph;
 
 	/* Get ivec. This can be wrong, check against another impls. */
 	if (esp->conf.ivlen)
@@ -204,12 +202,12 @@
 
 	/* ... check padding bits here. Silly. :-) */ 
 
+	iph = skb->nh.iph;
+	ihl = iph->ihl * 4;
+
 	if (x->encap) {
 		struct xfrm_encap_tmpl *encap = x->encap;
-		struct udphdr *uh;
-
-		uh = (struct udphdr *)(iph + 1);
-		encap_len = (void*)esph - (void*)uh;
+		struct udphdr *uh = (void *)(skb->nh.raw + ihl);
 
 		/*
 		 * 1) if the NAT-T peer's IP or port changed then
@@ -246,11 +244,7 @@
 
 	iph->protocol = nexthdr[1];
 	pskb_trim(skb, skb->len - alen - padlen - 2);
-	memcpy(workbuf, skb->nh.raw, iph->ihl*4);
-	skb->h.raw = skb_pull(skb, sizeof(struct ip_esp_hdr) + esp->conf.ivlen);
-	skb->nh.raw += encap_len + sizeof(struct ip_esp_hdr) + esp->conf.ivlen;
-	memcpy(skb->nh.raw, workbuf, iph->ihl*4);
-	skb->nh.iph->tot_len = htons(skb->len);
+	skb->h.raw = __skb_pull(skb, sizeof(*esph) + esp->conf.ivlen) - ihl;
 
 	return 0;
 
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 95278b2..8e24358 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -45,7 +45,6 @@
 static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err, plen, dlen;
-	struct iphdr *iph;
 	struct ipcomp_data *ipcd = x->data;
 	u8 *start, *scratch;
 	struct crypto_tfm *tfm;
@@ -74,8 +73,6 @@
 		
 	skb_put(skb, dlen - plen);
 	memcpy(skb->data, scratch, dlen);
-	iph = skb->nh.iph;
-	iph->tot_len = htons(dlen + iph->ihl * 4);
 out:	
 	put_cpu();
 	return err;
@@ -83,14 +80,9 @@
 
 static int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	u8 nexthdr;
 	int err = 0;
 	struct iphdr *iph;
-	union {
-		struct iphdr	iph;
-		char 		buf[60];
-	} tmp_iph;
-
+	struct ip_comp_hdr *ipch;
 
 	if ((skb_is_nonlinear(skb) || skb_cloned(skb)) &&
 	    skb_linearize(skb, GFP_ATOMIC) != 0) {
@@ -102,15 +94,10 @@
 
 	/* Remove ipcomp header and decompress original payload */	
 	iph = skb->nh.iph;
-	memcpy(&tmp_iph, iph, iph->ihl * 4);
-	nexthdr = *(u8 *)skb->data;
-	skb_pull(skb, sizeof(struct ip_comp_hdr));
-	skb->nh.raw += sizeof(struct ip_comp_hdr);
-	memcpy(skb->nh.raw, &tmp_iph, tmp_iph.iph.ihl * 4);
-	iph = skb->nh.iph;
-	iph->tot_len = htons(ntohs(iph->tot_len) - sizeof(struct ip_comp_hdr));
-	iph->protocol = nexthdr;
-	skb->h.raw = skb->data;
+	ipch = (void *)skb->data;
+	iph->protocol = ipch->nexthdr;
+	skb->h.raw = skb->nh.raw + sizeof(*ipch);
+	__skb_pull(skb, sizeof(*ipch));
 	err = ipcomp_decompress(x, skb);
 
 out:	
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index e46d9a4..a9e6b3d 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -38,8 +38,22 @@
 	return 0;
 }
 
+/* Remove encapsulation header.
+ *
+ * The IP header will be moved over the top of the encapsulation header.
+ *
+ * On entry, skb->h shall point to where the IP header should be and skb->nh
+ * shall be set to where the IP header currently is.  skb->data shall point
+ * to the start of the payload.
+ */
 static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 {
+	int ihl = skb->data - skb->h.raw;
+
+	if (skb->h.raw != skb->nh.raw)
+		skb->nh.raw = memmove(skb->h.raw, skb->nh.raw, ihl);
+	skb->nh.iph->tot_len = htons(skb->len + ihl);
+	skb->h.raw = skb->data;
 	return 0;
 }